Flow-based Speech Analysis

Flow-based Speech Analysis

• Members: Dong Wang, Haoran Sun, Yunqi Cai, Lantian Li
• Paper: Haoran Sun, Yunqi Cai, Lantian Li, Dong Wang, "On Investigation of Unsupervised Speech Factorization Based in Normalization Flow", 2019. paper

Introduction

We present a preliminary investigation on unsupervised speech factorization based on the normalization flow model. This model constructs a complex invertible transform, by which we can project speech segments into a latent code space where the distribution is a simple diagonal Gaussian. Our preliminary investigation on the TIMIT database shows that this code space exhibits favorable properties such as denseness and pseudo linearity, and perceptually important factors such as phonetic content and speaker trait can be represented as particular directions within the code space.